© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 90433
    Prev
    Next
    INDEX
    Explanations

    connectors and subsequent entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    优质
    0.23
    TabText
    0.22
     sunset
    0.22
    obi
    0.22
     digitar
    0.22
     נא
    0.22
    書法
    0.22
    ૄ
    0.22
     sweet
    0.22
     rů
    0.22
    POSITIVE LOGITS
     তাদের
    0.24
     者
    0.22
    vind
    0.22
    자와
    0.21
     their
    0.21
     authorities
    0.21
    bff
    0.21
     તેમના
    0.21
     dejando
    0.21
     کھیل
    0.21
    Activations Density 0.007%

    No Known Activations